[WIP] Integrates JorgeKFAC with diffusion model training script #3
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
keshprad
commented
Jan 7, 2025
improved_diffusion/respace.py
Outdated
| terms["loss_sampled"] = mean_flat((y_sampled - model_output) ** 2) | ||
| if "vb" in terms: | ||
| terms["loss"] = terms["mse"] + terms["vb"] | ||
| # TODO: Should terms["vb"] be added to terms["loss_sampled"]? |
There was a problem hiding this comment.
Should terms["vb"] be added to terms["loss_sampled"]?
There was a problem hiding this comment.
Most likely "vb" shouldn't be in terms. Can you check and let me know?
keshprad
commented
Jan 7, 2025
| loss_sampled = (losses["loss_sampled"] * weights).mean() | ||
| loss_sampled.backward(retain_graph=True) | ||
| self.opt.acc_stats = False | ||
| self.opt.zero_grad() # clear the gradient for computing true-fisher | ||
|
|
||
| if isinstance(self.schedule_sampler, LossAwareSampler): | ||
| self.schedule_sampler.update_with_local_losses( |
There was a problem hiding this comment.
I don't understand what L233 (self.schedule_sampler.update_with_local_losses) does. Should anything here be modified to do similar for losses["loss_sampled"]?
There was a problem hiding this comment.
I don't think we need to use the proxy loss (i.e. loss_sampled) anywhere in this function. This can remain untouched.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.